Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.5-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
e26004f
·
verified ·
1 Parent(s): e110732

Training in progress, step 100

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +6 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18699039542be26a6de26fd614ce83ebf19bf43154bf52cde609cc3dd28f796e
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fee6d11dabb19fab727c742912ef7d629cf6a6e151910e56c72a64d4c899f3c
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -4,3 +4,9 @@
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.9403, "accuracy": 0.4000000059604645, "learning_rate": 4.9912321481237616e-06, "epoch": 0.042643923240938165, "percentage": 2.67, "elapsed_time": "0:05:07", "remaining_time": "3:06:49", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.9588, "accuracy": 0.4749999940395355, "learning_rate": 4.986304738420684e-06, "epoch": 0.053304904051172705, "percentage": 3.33, "elapsed_time": "0:06:25", "remaining_time": "3:06:16", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9551004767417908, "epoch": 0.053304904051172705, "percentage": 3.33, "elapsed_time": "0:06:46", "remaining_time": "3:16:38", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.9403, "accuracy": 0.4000000059604645, "learning_rate": 4.9912321481237616e-06, "epoch": 0.042643923240938165, "percentage": 2.67, "elapsed_time": "0:05:07", "remaining_time": "3:06:49", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.9588, "accuracy": 0.4749999940395355, "learning_rate": 4.986304738420684e-06, "epoch": 0.053304904051172705, "percentage": 3.33, "elapsed_time": "0:06:25", "remaining_time": "3:06:16", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9551004767417908, "epoch": 0.053304904051172705, "percentage": 3.33, "elapsed_time": "0:06:46", "remaining_time": "3:16:38", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 60, "total_steps": 1500, "loss": 0.9636, "accuracy": 0.4625000059604645, "learning_rate": 4.980286753286196e-06, "epoch": 0.06396588486140725, "percentage": 4.0, "elapsed_time": "0:08:09", "remaining_time": "3:15:39", "throughput": "0.00", "total_tokens": 0}
8
+ {"current_steps": 70, "total_steps": 1500, "loss": 0.9677, "accuracy": 0.36250001192092896, "learning_rate": 4.973180832407471e-06, "epoch": 0.07462686567164178, "percentage": 4.67, "elapsed_time": "0:09:28", "remaining_time": "3:13:24", "throughput": "0.00", "total_tokens": 0}
9
+ {"current_steps": 80, "total_steps": 1500, "loss": 0.9609, "accuracy": 0.42500001192092896, "learning_rate": 4.964990092676263e-06, "epoch": 0.08528784648187633, "percentage": 5.33, "elapsed_time": "0:10:43", "remaining_time": "3:10:24", "throughput": "0.00", "total_tokens": 0}
10
+ {"current_steps": 90, "total_steps": 1500, "loss": 0.9587, "accuracy": 0.4749999940395355, "learning_rate": 4.9557181268217225e-06, "epoch": 0.09594882729211088, "percentage": 6.0, "elapsed_time": "0:11:56", "remaining_time": "3:07:02", "throughput": "0.00", "total_tokens": 0}
11
+ {"current_steps": 100, "total_steps": 1500, "loss": 0.9548, "accuracy": 0.5625, "learning_rate": 4.9453690018345144e-06, "epoch": 0.10660980810234541, "percentage": 6.67, "elapsed_time": "0:13:12", "remaining_time": "3:05:00", "throughput": "0.00", "total_tokens": 0}
12
+ {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.947841465473175, "epoch": 0.10660980810234541, "percentage": 6.67, "elapsed_time": "0:13:34", "remaining_time": "3:10:00", "throughput": "0.00", "total_tokens": 0}